{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T06:18:52Z","timestamp":1774678732744,"version":"3.50.1"},"reference-count":36,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2021,8,1]],"date-time":"2021-08-01T00:00:00Z","timestamp":1627776000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,8,1]],"date-time":"2021-08-01T00:00:00Z","timestamp":1627776000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,8,1]],"date-time":"2021-08-01T00:00:00Z","timestamp":1627776000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Institute of Information & communications Technology Planning & Evaluation","award":["2021-0-00467"],"award-info":[{"award-number":["2021-0-00467"]}]},{"name":"Intelligent 6G Wireless Access System","award":["2021-0-00106"],"award-info":[{"award-number":["2021-0-00106"]}]},{"name":"Basic Science Research Programs"},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Ministry of Science and ICT","award":["2019R1C1C1006806"],"award-info":[{"award-number":["2019R1C1C1006806"]}]},{"name":"Ministry of Science and ICT","award":["2021R1A4A1030898"],"award-info":[{"award-number":["2021R1A4A1030898"]}]},{"name":"NRF"},{"DOI":"10.13039\/100010449","name":"Ministry of Education","doi-asserted-by":"publisher","award":["NRF5199991514504"],"award-info":[{"award-number":["NRF5199991514504"]}],"id":[{"id":"10.13039\/100010449","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CCF-1908308"],"award-info":[{"award-number":["CCF-1908308"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Sel. Top. Signal Process."],"published-print":{"date-parts":[[2021,8]]},"DOI":"10.1109\/jstsp.2021.3091842","type":"journal-article","created":{"date-parts":[[2021,6,23]],"date-time":"2021-06-23T19:48:26Z","timestamp":1624477706000},"page":"1258-1271","source":"Crossref","is-referenced-by-count":3,"title":["Shallow Reinforcement Learning for Energy Harvesting Communications With Imperfect Channel Knowledge"],"prefix":"10.1109","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3860-8962","authenticated-orcid":false,"given":"Heasung","family":"Kim","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6804-980X","authenticated-orcid":false,"given":"Jungwoo","family":"Lee","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6513-1237","authenticated-orcid":false,"given":"Wonjae","family":"Shin","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2062-131X","authenticated-orcid":false,"given":"H. Vincent","family":"Poor","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref32","first-page":"3790","article-title":"Monotonic calibrated interpolated look-up tables","volume":"17","author":"gupta","year":"2016","journal-title":"J Mach Learn Res"},{"key":"ref31","article-title":"Deep reinforcement learning in large discrete action spaces","author":"dulac-arnold","year":"2015"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.2307\/20062066"},{"key":"ref36","first-page":"1352","article-title":"Reinforcement learning with deep energy-based policies","author":"haarnoja","year":"2017","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref35","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref34","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"glorot","year":"2010","journal-title":"Proc 13th Int Conf Artif Intell Statist"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2013.030413.121120"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2012.032812.110813"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2013.2295603"},{"key":"ref13","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"2000","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref14","first-page":"1","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"Proc NIPS 13th Workshop Deep Learn"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2016.7511405"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TGCN.2017.2703855"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3026362"},{"key":"ref18","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/GLOCOM.2018.8647681"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/18.995552"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2013.2283505"},{"key":"ref27","author":"cover","year":"2012","journal-title":"Elements of Information Theory"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2012.2199984"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2011.120911.101813"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1515\/9781400822539"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2013.130811"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2016.2548459"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2016.2611858"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2012.012412.110805"},{"key":"ref9","author":"puterman","year":"2014","journal-title":"Markov Decision Processes Discrete Stochastic Dynamic Programming"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2011.110921"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2019.2921159"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/3897.001.0001"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2911544"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2020.3018827"},{"key":"ref23","article-title":"A study on overfitting in deep reinforcement learning","author":"zhang","year":"2018"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/18.841172"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2006.872984"}],"container-title":["IEEE Journal of Selected Topics in Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/4200690\/9564084\/09463730.pdf?arnumber=9463730","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:52:42Z","timestamp":1652194362000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9463730\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8]]},"references-count":36,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/jstsp.2021.3091842","relation":{},"ISSN":["1932-4553","1941-0484"],"issn-type":[{"value":"1932-4553","type":"print"},{"value":"1941-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,8]]}}}